{
  "best_metric": 0.42944997549057007,
  "best_model_checkpoint": "local_model_directory/checkpoint-47",
  "epoch": 9.904761904761905,
  "eval_steps": 500,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9523809523809523,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 5.0407,
      "step": 5
    },
    {
      "epoch": 0.9523809523809523,
      "eval_loss": 4.816819190979004,
      "eval_runtime": 4.4668,
      "eval_samples_per_second": 37.61,
      "eval_steps_per_second": 4.701,
      "step": 5
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 8.692849159240723,
      "learning_rate": 0.00019839357429718877,
      "loss": 3.5268,
      "step": 10
    },
    {
      "epoch": 1.9047619047619047,
      "eval_loss": 2.1233882904052734,
      "eval_runtime": 4.4662,
      "eval_samples_per_second": 37.616,
      "eval_steps_per_second": 4.702,
      "step": 10
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 7.133273601531982,
      "learning_rate": 0.0001963855421686747,
      "loss": 1.9397,
      "step": 15
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 1.2800443172454834,
      "eval_runtime": 4.4631,
      "eval_samples_per_second": 37.642,
      "eval_steps_per_second": 4.705,
      "step": 15
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.404087066650391,
      "learning_rate": 0.00019397590361445782,
      "loss": 1.0223,
      "step": 21
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7716784477233887,
      "eval_runtime": 4.4654,
      "eval_samples_per_second": 37.622,
      "eval_steps_per_second": 4.703,
      "step": 21
    },
    {
      "epoch": 4.9523809523809526,
      "grad_norm": 8.276748657226562,
      "learning_rate": 0.00019196787148594377,
      "loss": 0.8135,
      "step": 26
    },
    {
      "epoch": 4.9523809523809526,
      "eval_loss": 0.5757163763046265,
      "eval_runtime": 4.4645,
      "eval_samples_per_second": 37.63,
      "eval_steps_per_second": 4.704,
      "step": 26
    },
    {
      "epoch": 5.904761904761905,
      "grad_norm": 3.8597450256347656,
      "learning_rate": 0.00018995983935742974,
      "loss": 0.6574,
      "step": 31
    },
    {
      "epoch": 5.904761904761905,
      "eval_loss": 0.5177809596061707,
      "eval_runtime": 4.4665,
      "eval_samples_per_second": 37.613,
      "eval_steps_per_second": 4.702,
      "step": 31
    },
    {
      "epoch": 6.857142857142857,
      "grad_norm": 4.316291332244873,
      "learning_rate": 0.00018795180722891569,
      "loss": 0.5833,
      "step": 36
    },
    {
      "epoch": 6.857142857142857,
      "eval_loss": 0.4853830933570862,
      "eval_runtime": 4.465,
      "eval_samples_per_second": 37.626,
      "eval_steps_per_second": 4.703,
      "step": 36
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.386613607406616,
      "learning_rate": 0.0001855421686746988,
      "loss": 0.4549,
      "step": 42
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4494071304798126,
      "eval_runtime": 4.4635,
      "eval_samples_per_second": 37.638,
      "eval_steps_per_second": 4.705,
      "step": 42
    },
    {
      "epoch": 8.952380952380953,
      "grad_norm": 2.4768359661102295,
      "learning_rate": 0.00018353413654618474,
      "loss": 0.5012,
      "step": 47
    },
    {
      "epoch": 8.952380952380953,
      "eval_loss": 0.42944997549057007,
      "eval_runtime": 4.465,
      "eval_samples_per_second": 37.626,
      "eval_steps_per_second": 4.703,
      "step": 47
    },
    {
      "epoch": 9.904761904761905,
      "grad_norm": 3.0964863300323486,
      "learning_rate": 0.0001815261044176707,
      "loss": 0.514,
      "step": 52
    },
    {
      "epoch": 9.904761904761905,
      "eval_loss": 0.45047804713249207,
      "eval_runtime": 4.4637,
      "eval_samples_per_second": 37.637,
      "eval_steps_per_second": 4.705,
      "step": 52
    },
    {
      "epoch": 9.904761904761905,
      "step": 52,
      "total_flos": 1735676016721920.0,
      "train_loss": 1.4758788301394536,
      "train_runtime": 173.2572,
      "train_samples_per_second": 96.966,
      "train_steps_per_second": 2.886
    }
  ],
  "logging_steps": 500,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.1
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1735676016721920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}